Returns the frequency-weighted mean and variance of `x`. Args: x: A tensor. axes: 1-d tensor of int32 values; these are the axes along which to compute mean and variance. frequency_weights: A tensor of positive weights which can be broadcast with x. keepdims: Produce m
(x, axes, frequency_weights, keepdims=False, name=None)
| 1448 | |
| 1449 | @tf_export("nn.weighted_moments", v1=[]) |
| 1450 | def weighted_moments_v2(x, axes, frequency_weights, keepdims=False, name=None): |
| 1451 | """Returns the frequency-weighted mean and variance of `x`. |
| 1452 | |
| 1453 | Args: |
| 1454 | x: A tensor. |
| 1455 | axes: 1-d tensor of int32 values; these are the axes along which |
| 1456 | to compute mean and variance. |
| 1457 | frequency_weights: A tensor of positive weights which can be |
| 1458 | broadcast with x. |
| 1459 | keepdims: Produce moments with the same dimensionality as the input. |
| 1460 | name: Name used to scope the operation. |
| 1461 | |
| 1462 | Returns: |
| 1463 | Two tensors: `weighted_mean` and `weighted_variance`. |
| 1464 | """ |
| 1465 | return weighted_moments( |
| 1466 | x=x, |
| 1467 | axes=axes, |
| 1468 | frequency_weights=frequency_weights, |
| 1469 | name=name, |
| 1470 | keep_dims=keepdims) |
| 1471 | |
| 1472 | |
| 1473 | @tf_export("nn.batch_normalization") |
nothing calls this directly
no test coverage detected